File size: 3,393 Bytes
7ab7df1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed005f8
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
"""Pytest configuration and shared fixtures."""

import os
from unittest.mock import MagicMock, Mock

import pytest
from langchain_core.documents import Document
from langchain_core.messages import AIMessage, HumanMessage


@pytest.fixture
def mock_embeddings():
    """Create a mock embeddings model."""
    mock = MagicMock()
    mock.embed_query.return_value = [0.1] * 384
    return mock


@pytest.fixture
def mock_vectorstore():
    """Create a mock vectorstore."""
    mock = MagicMock()
    mock.get.return_value = {
        "documents": ["Document 1", "Document 2"],
        "metadatas": [
            {"source": "pdf/test1.pdf", "page": 1},
            {"source": "pdf/test2.pdf", "page": 2},
        ],
    }
    return mock


@pytest.fixture
def sample_documents():
    """Create sample document objects."""
    return [
        Document(
            page_content="This is a test document about machine learning.",
            metadata={"source": "pdf/test1.pdf", "page": 1},
        ),
        Document(
            page_content="Another document about neural networks.",
            metadata={"source": "pdf/test2.pdf", "page": 2},
        ),
        Document(
            page_content="Document in references section.",
            metadata={"source": "pdf/test3.pdf", "page": 3, "section": "references"},
        ),
    ]


@pytest.fixture
def mock_llm():
    """Create a mock LLM."""
    mock = MagicMock()
    mock.invoke.return_value = MagicMock(content="Mocked response")
    mock.stream.return_value = [
        MagicMock(content="Chunk "),
        MagicMock(content="1 "),
        MagicMock(content="2"),
    ]
    return mock


@pytest.fixture
def mock_reranker():
    """Create a mock reranker."""
    mock = MagicMock()
    mock.predict.return_value = [0.9, 0.8, 0.7]
    return mock


@pytest.fixture
def sample_chat_history():
    """Create sample chat history."""
    return [
        {"role": "user", "content": "What is RAG?"},
        {"role": "assistant", "content": "RAG is Retrieval-Augmented Generation."},
        {"role": "user", "content": "How does it work?"},
    ]


@pytest.fixture
def sample_chat_history_tuples():
    """Create sample chat history as tuples."""
    return [
        ("What is RAG?", "RAG is Retrieval-Augmented Generation."),
        ("How does it work?", "It retrieves documents and generates answers."),
    ]


@pytest.fixture
def temp_pdf_dir(tmp_path):
    """Create a temporary directory for PDF files."""
    pdf_dir = tmp_path / "pdf"
    pdf_dir.mkdir()
    return str(pdf_dir)


@pytest.fixture
def temp_vectorstore_dir(tmp_path):
    """Create a temporary directory for vectorstore."""
    vs_dir = tmp_path / "vectorstore"
    vs_dir.mkdir()
    return str(vs_dir)


@pytest.fixture
def mock_hybrid_results():
    """Create mock hybrid search results."""
    doc1 = Document(
        page_content="Test content 1",
        metadata={"source": "pdf/test1.pdf", "page": 1},
    )
    doc2 = Document(
        page_content="Test content 2",
        metadata={"source": "pdf/test2.pdf", "page": 2},
    )
    return [
        {
            "doc": doc1,
            "fused_score": 0.9,
            "semantic_score": 0.85,
            "keyword_score": 0.95,
        },
        {
            "doc": doc2,
            "fused_score": 0.8,
            "semantic_score": 0.75,
            "keyword_score": 0.85,
        },
    ]